Hello!
> First of all, I thank you for the response. But one thing I could not
> understand is the term "prototype". Is it that the CSZ will not work even
> if I enable it in the kernel !!!
You cannot enable it.
> Or, if I am able to write an interface in
> the 'tc', should that allow me to use CSZ properly ?
Yes, certainly. You may try this. Only this work does not deserve
efforts, I think. Classical WFQ is not designed to make any real work.
Actually, it is easier to write new schduler from scratchm than update
shc_csz f.e. to make wfq2+.
> I would surely want to try a hand on it. Any pointers to understand the
> H-PFQ algorithm first ? ;-)
Papers by their inventors. F.e. references and ps copies may be found
at LBNL NRG home page.
Alexey Kuznetsov
-
To unsubscribe from this list: send the line "unsubscribe linux-net" in
the body of a message to [EMAIL PROTECTED]
